Curated topic · 6 ARTICLES
Explore practical Context Engineering articles grounded in clear explanations and engineering tradeoffs.
Latest articles
A larger context window is not inherently better; higher relevance is. This article summarizes four strategies—selective loading, summarization, isolation, and externalization—for using a finite window like a budget, along with design criteria for always-loaded files such as CLAUDE.md.
Read articleAfter working with AI for a while, something odd happens. It asks again about conditions you clearly set earlier, undoes fixes made above, and quietly ignores instructions from the start of the conversation. Even pointing out, “I already told you that,” helps only briefly. It isn’t broken. This comes from how AI itself handles conversation memory, and once you understand the principle, the solution is simple.
Read articleIn earlier installments, we explored ways to conserve context: clear history at each work boundary (Part 3) and keep fixed overhead short (Part 4). Yet some tasks remain too large to handle. A typical example is, “Figure out how payment logic flows through this codebase.” A diligent agent would read dozens of files, and as we saw in Part 1, everything it reads accumulates in context. By the time the investigation is complete, no context remains for the actual work that knowledge enables—changing the code.
Read articleWhen using a coding agent like Claude Code, you may see a warning such as "Context left until auto-compact: 8%" at the bottom of the screen. Chat-based AI does not usually show this. Yet surprisingly few people can explain why the number decreases or what happens when it reaches zero…
Read articleIn Part 1, we saw why the context window is finite. But looking at today's model specs raises a question: models with 1 million tokens already exist, so why not just feed in the entire codebase or document? Is there any point in being careful?
Read articleThe previous two posts completed the diagnosis. The context window is finite (Part 1), and filling it does not mean everything is used; performance actually declines as it grows (Part 2). The prescription is clear: manage context. Coding agents, including Claude Code, provide /clear and /compact for this purpose…
Read article